When unpolished glutinous rice is dried, the translucent grains become white and completely opaque. This phenomenon is called ‘ryokuka’ in Japanese, and distinguishes glutinous rice from non-glutinous rice. Opaqueness is a factor in glutinous rice quality. However, over-drying to achieve opaqueness can result in an increase in cracked or broken rice kernels, which lowers quality. Methods for detecting cracked kernels of non-glutinous rice have been established, but these cannot be applied to glutinous rice owing to its opaqueness. We developed a method for detecting cracked kernels in unpolished glutinous rice that relies on diffuse-reflection spectral imaging. The method uses spectral filters and oblique lightning from a halogen light source. We tested illumination methods and wavelengths, using unpolished kernels of ‘Hakucho-mochi’ glutinous rice, grown in Hokkaido. Cracked and normal kernels were observed under visible to near-infrared light. Light in the range of 500 to 1,100 nm enabled clear detection of the cracks in the kernels. Since cracks tend to occur along the short axis of the rice kernel, more cracked kernels could be detected with illumination parallel to the long axis. Using these results, we developed a portable device for detecting cracked kernels in collaboration with Kett Electric Laboratory. The device can detect cracked kernels in unpolished glutinous rice at low cost anywhere.

View full abstract

Agricultural information processing systems using geographical information system–compatible paddy field maps have been proposed as a way to increase efficiency for regional farmers. But producing paddy field maps is time consuming, because the maps are drawn by hand. We recently reported a “raster–vector conversion” method, which automatically creates paddy field maps in vector format from binarized cadastral images in raster format on a personal computer. Here we report a method to automatically create paddy field maps from aerial orthophotographs (digital orthophoto data). For efficient processing of large aerial photographs in which paddy fields can be regarded as small areas with specific characteristics, we used the efficient graph-based image segmentation method, which allows efficient area segmentation, to automatically create maps, and our raster–vector conversion method to convert segmented areas from raster images to shape files. The mean identification rate of paddy fields at the local scale in 13 aerial orthophotographs was 29%.

View full abstract

Results of the 2010 Agriculture Census of Japan show signs of the recultivation of marginal farmland, but reconfirm the structural deterioration of agriculture in Japan. With the return of the Abe administration, again pushing to weaken the yen and partake in the Trans-Pacific Partnership, international competition for farmers is about to worsen. Forging strong and resilient agriculture under these circumstances requires the strategic prioritization of efficient measures to meet the future needs of Japan. This study was conducted on the understanding that policies need to account for regional characteristics of agricultural areas. It reveals, by region, factors responsible for farm exit that in turn affect the structure of agriculture. Results of the 2005 and 2010 censuses were linked, yielding data on 206 characteristics (variables) of 1.9 million farm households (cases). The dataset was statistically analyzed to identify factors associated with farm exit. In many regions, the factors that emerged were those typically associated with exit, such as old age, absence of successors, and small scale of operation. However, other factors, such as farm management style and attitude toward participation in shared-use organizations, also affected farm exit in varying ways depending on the region. This discovery of regionally unique farm exit factors will contribute basic support for future policy design. This study makes a further contribution in its analytical methodology. Errors that occur in the process of estimating measurement models of large datasets were investigated, and countermeasures such as the formulation of subsamples were devised. Empirical findings on this innovative methodology for the quantitative analysis of individual censuses expand the academic knowledge base on agricultural informatics and will further the development of this field.

View full abstract

Agricultural workers can find it difficult to train new workers and to stay safe. To overcome these problems, we developed wearable sensors to record and analyze workers’ motions. To gather background information, we reviewed a wide range of sources (e.g., industrial goods, patents, and academic papers), discussed needs with agricultural informatics researchers, workers, and farm managers, and selected devices to monitor workers’ actions. First, we measured acceleration and angular velocity when subjects posed in typical postures and performed typical actions. Next, on small to medium-size farms, we logged the acceleration and angular velocity of the lower arms, chest, waist, and tools. A laptop computer in a knapsack on the back of each subject gathered and analyzed the data, using statistical and human dynamics software that we wrote. At the same time, we recorded the users’ actions from a few meters away on a fixed digital video camera. We then analyzed the data, mainly by optical flow methods. By analyzing various statistical differences concerning acceleration data between experienced and inexperienced workers and by showing (illustrating) the results to the workers for checking them and for utilizing them to revise workers’ movements, we confirmed the validity and usefulness of the system. The results, which need to be validated more precisely, will enhance workers’ skills and safety, and allow critical situations (e.g., risks of falling and injury) to be diagnosed. These techniques could be applied to other areas, being economical, robust, scalable, and easily distributed.

View full abstract

To clarify how risk and information are managed in a farming corporation and the relationship between them and human resources development, we conducted a case study of a large-scale vegetable farm. To understand risk management, we analyzed how information is managed, what tools are used, how each tool is used, and their relations. The farm fully utilized several information and communications technology (ICT) tools and database systems to full capacity to manage information on risks and to achieve strategic management, tactical management, and control. The results show that farm risk management requires the effective management of huge amounts of information. These ICT tools are indispensable to advanced farming management.

View full abstract

In the Japanese language, the word “Kansei” is used to indicate mental states or activities that occur in response to stimulation from the outside world. For example, emotion is defined as a component of Kansei. In the West, words such as sensibility and perceptiveness are often used with meanings similar to Kansei. Furthermore, in the Japanese field of Kansei engineering, designers strive to integrate human feelings and sensibilities more closely with manufacturing and production activities. Accordingly, if Kansei-related information can be extracted in various situations, it is believed that distinctive design, development, and evaluation processes become possible. In this paper, we describe the fabrication of an inexpensive and near real-time system capable of extracting Kansei information from user facial expressions. To accomplish this, we developed a computer vision system using the free OpenCV image-processing library. The characteristic values calculated from these inputs were the variation (the normalized polygon area change ratio) of four items: the inner end of the eyebrows, the upper and lower parts of the eyes, and the corners of the mouth, which were then calculated using seven face nodes. Three Kansei information types were targeted: positive Kansei information (appreciation, fun, and happiness), negative Kansei information (unpleasantness and distaste), and Kansei information associated with shock or surprise. With the assistance of 12 test subjects, we began working to obtain specific Kansei knowledge, and quickly determined that the relationships between facial expressions and Kansei information were highly individual in nature. Therefore, in the next stage, we formulated an algorithm to discriminate the three Kansei information types while focusing on a single subject, and obtained good results. However, since facial reactions vary significantly between individual human beings, it is currently necessary to prepare a seven-point template image in advance for each person to be examined, and then to adjust the algorithm parameters after measuring their facial expressions in order to obtain Kansei information. Despite these initial difficulties, our results show that an inexpensive and near real-time computer vision system capable of extracting facial expression Kansei information can be constructed. We believe that such systems can make it possible to apply Kansei information decision support to a variety of automatic evaluation and design processes.

View full abstract

As the agricultural workforce in Japan ages, fostering the next generation of farmers is critical. Agricultural schools are an important point of entry into the sector, and there is a need to share the appeal of agriculture as a field of study and as an occupation among young people. Japanese agriculture is currently at a major crossroads regarding issues such as the Trans-Pacific Partnership negotiations. Japanese subcultures offer a potential solution. Subcultures such as anime (cartoons), manga (comics), and anthropomorphic characters are well known, both in Japan and abroad. Such subcultures offer the potential advantages of making real places sacred; securing new marketing segments through effective character-based branding; increasing publicity through local characters; and stimulating interest in and increasing the popularity of agriculture and agricultural schools through comics set in that context. Although many such initiatives have been launched to date, there have been numerous failures, and many of the successes have been short lived. We conducted a survey and analyzed the long-term factors affecting the success of Japanese-style subculture strategies, and how these could be used to combine the concept of yaowarashi (yao = all, warashi = children) with agriculture to encourage people to enter agriculture. This paper reports on the yaowarashi initiative and the current state of yaowarashi activities and achievements. Measures to stimulate academic and employment interest in yaowarashi are discussed. Most respondents had high expectations for the future.

View full abstract